Service Level Agreement Aware Resource Access Latency Minimization

3. The method of claim 2, wherein the plurality of regions correspond to a plurality of different computer systems or storage systems physically located remotely from each other.

4. The method of claim 1, wherein selecting the distribution of computer resources comprises selecting the distribution of computer resources whose corresponding computer simulation generates simulation results that meet the at least one SLA performance metric and whose simulation results are closest to the at least one SLA performance metric relative to simulation results of other ones of the plurality of computer simulations.

5. The method of claim 1, wherein, in response to none of the simulation results of the plurality of computer simulations achieving a performance that meets the at least one SLA performance metric, selecting the distribution of computing resources comprises selecting the distribution of computer resources corresponding to a computer simulation whose simulation results do not meet the at least one SLA performance metric, but is closest to the at least one SLA performance metric relative to simulation results of other ones of the plurality of computer simulations.

6. The method of claim 1, wherein the computing resources comprise data structures stored in a plurality of different data storage systems and the computer operation is a computer operation for accessing the data structures from the plurality of different data storage systems, and wherein redistributing the computing resources of the distributed data processing system in accordance with the selected distribution of computing resources comprises migrating or replicating one or more of the data structures to different data storage systems to reduce latency in accessing the one or more data structures.

7. The method of claim 1, wherein the SLA performance metric is a measure of latency in performing the computer operation.

8. The method of claim 7, wherein the measure of latency is a round trip time for performing the computer operation.

9. The method of claim 1, wherein the distributed data processing system is a distributed data center.

10. The method of claim 9, wherein the distributed data center is hosted by one or more service providers of a cloud-based computing system.

13. The computer program product of claim 12, wherein the plurality of regions correspond to a plurality of different computer systems or storage systems physically located remotely from each other.

14. The computer program product of claim 11, wherein selecting the distribution of computer resources comprises selecting the distribution of computer resources whose corresponding computer simulation generates simulation results that meet the at least one SLA performance metric and whose simulation results are closest to the at least one SLA performance metric relative to simulation results of other ones of the plurality of computer simulations.

15. The computer program product of claim 11, wherein, in response to none of the simulation results of the plurality of computer simulations achieving a performance that meets the at least one SLA performance metric, selecting the distribution of computing resources comprises selecting the distribution of computer resources corresponding to a computer simulation whose simulation results do not meet the at least one SLA performance metric, but is closest to the at least one SLA performance metric relative to simulation results of other ones of the plurality of computer simulations.

16. The computer program product of claim 11, wherein the computing resources comprise data structures stored in a plurality of different data storage systems and the computer operation is a computer operation for accessing the data structures from the plurality of different data storage systems, and wherein redistributing the computing resources of the distributed data processing system in accordance with the selected distribution of computing resources comprises migrating or replicating one or more of the data structures to different data storage systems to reduce latency in accessing the one or more data structures.

17. The computer program product of claim 11, wherein the SLA performance metric is a measure of latency in performing the computer operation.

18. The computer program product of claim 17, wherein the measure of latency is a round trip time for performing the computer operation.

19. The computer program product of claim 11, wherein the distributed data processing system is a distributed data center.